Re: [PATCH v4 20/32] drm/xe/survivability: Report 'boot status' using SIGID

On 13-08-2026 02:58 pm, Michal Wajdeczko wrote:
>
> On 8/13/2026 10:38 AM, Mallesh, Koujalagi wrote:
>> On 13-08-2026 12:44 am, Michal Wajdeczko wrote:
>>> Report 'boot status' details using xe_log_err_fatal/info() macros.
>>> While around, move static helper code closer to the caller and let
>>> it take xe instead of pdev.
>>>
>>> Signed-off-by: Michal Wajdeczko <[email protected]>
>>> Cc: Rodrigo Vivi <[email protected]>
>>> Cc: Riana Tauro <[email protected]>
>>> Cc: Aravind Iddamsetty <[email protected]>
>>> Cc: Mallesh Koujalagi <[email protected]>
>>> ---
>>>   drivers/gpu/drm/xe/xe_survivability_mode.c | 35 ++++++++++++----------
>>>   1 file changed, 19 insertions(+), 16 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
>>> index 4c506027fa94..85b4c125a217 100644
>>> --- a/drivers/gpu/drm/xe/xe_survivability_mode.c
>>> +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
>>> @@ -14,6 +14,7 @@
>>>   #include "xe_device.h"
>>>   #include "xe_heci_gsc.h"
>>>   #include "xe_i2c.h"
>>> +#include "xe_log.h"
>>>   #include "xe_mmio.h"
>>>   #include "xe_nvm.h"
>>>   #include "xe_pcode_api.h"
>>> @@ -172,21 +173,6 @@ static void populate_survivability_info(struct xe_device *xe)
>>>   	}
>>>   }
>>>   
>>> -static void log_survivability_info(struct pci_dev *pdev)
>>> -{
>>> -	struct xe_device *xe = pdev_to_xe_device(pdev);
>>> -	struct xe_survivability *survivability = &xe->survivability;
>>> -	u32 *info = survivability->info;
>>> -	int id;
>>> -
>>> -	dev_info(&pdev->dev, "Survivability Boot Status : Critical Failure (%d)\n",
>>> -		 survivability->boot_status);
>>> -	for (id = 0; id < MAX_SCRATCH_REG; id++) {
>>> -		if (info[id])
>>> -			dev_info(&pdev->dev, "%s: 0x%x\n", reg_map[id], info[id]);
>>> -	}
>>> -}
>>> -
>>>   static int check_boot_failure(struct xe_device *xe)
>>>   {
>>>   	struct xe_survivability *survivability = &xe->survivability;
>>> @@ -429,6 +415,23 @@ void xe_survivability_mode_runtime_enable(struct xe_device *xe)
>>>   	dev_err(&pdev->dev, "Firmware flash required, Please refer to the userspace documentation for more details!\n");
>>>   }
>>>   
>>> +static void log_survivability_info(struct xe_device *xe)
>>> +{
>>> +	struct xe_survivability *survivability = &xe->survivability;
>>> +	u32 *info = survivability->info;
>>> +	int id;
>>> +
>>> +	xe_log_err_fatal(xe, SURVIVABILITY, -ENXIO, "Boot Status: %s (%u)\n",
>>> +			 survivability->boot_status == CRITICAL_FAILURE ?
>>> +			 "Critical Failure" : "Other", survivability->boot_status);
>> Since log_survivability_info is called when survivability->boot_status == CRITICAL_FAILURE true, so please use "Critical Failure"  string directly.
> well, that's the current usage and function name didn't strictly say "log critical failure" only
>
> btw, printing fixed "Critical Failure" string followed by flexible %d also doesn't make sense IMO
>
> that's why I decided to make this function more flexible and reusable if needed

Totally agreed, u made it generic one, however current usage, we never 
going to hit "Other" case, which is dead here.

btw, "Other" is "Non Critical Failure" right?


Thanks,

-/Mallesh

>
>> Reviewed-by: Mallesh Koujalagi <[email protected]>
>>
>>> +
>>> +	for (id = 0; id < MAX_SCRATCH_REG; id++) {
>>> +		if (!info[id])
>>> +			continue;
>>> +		xe_log_info(xe, SURVIVABILITY, "%s: %#x\n", reg_map[id], info[id]);
>>> +	}
>>> +}
>>> +
>>>   /**
>>>    * xe_survivability_mode_boot_enable - Initialize and enable boot survivability mode
>>>    * @xe: xe device instance
>>> @@ -452,7 +455,7 @@ int xe_survivability_mode_boot_enable(struct xe_device *xe)
>>>   	 * v2 supports survivability mode for critical errors
>>>   	 */
>>>   	if (survivability->version < 2  && survivability->boot_status == CRITICAL_FAILURE) {
>>> -		log_survivability_info(pdev);
>>> +		log_survivability_info(xe);
>>>   		return -ENXIO;
>>>   	}
>>>